Browsing by Author "Cardoso, Pedro J. S."
Now showing 1 - 10 of 19
Results Per Page
Sort Options
- A computer vision based web application for tracking soccer playersPublication . Rodrigues, J. M. F.; Cardoso, Pedro J. S.; Vilas, Tiago; Silva, Bruno; Rodrigues, Pedro; Belguinha, António; Gomes, CarlosSoccer is a sport where everyone that is involved with it make all the efforts aiming for excellence. Not only the players need to show their skills on the pitch but also the coach, and the remaining staff, need to have their own tools so that they can perform at higher levels. Footdata is a project to build a new web application product for soccer (football), which integrates two fundamental components of this sport’s world: the social and the professional. While the former is an enhanced social platform for soccer professionals and fans, the later can be considered as a Soccer Resource Planning, featuring a system for acquisition and processing information to meet all the soccer management needs. In this paper we focus only in a specific module of the professional component. We will describe the section of the web application that allows to analyse movements and tactics of the players using images directly taken from the pitch or from videos, we will show that it is possible to draw players and ball movements in a web application and detect if those movements occur during a game.
- A distributed load scheduling mechanism for micro gridsPublication . Monteiro, J. M.; Eduardo, J.; Cardoso, Pedro J. S.; Semiao, J.Several protocols have recently been defined for smart grids that enable the communication between electric devices and energy management systems. While these protocols and architectures can already be applied in different fields of micro grids, it is still not clear how the distributed resources and constraints of such electrical grids can be managed in an optimum way. In order to achieve a reduction in electricity costs and maximizing investments made in renewable sources, an optimization mechanism should be used to perform load scheduling, considering different variables such as forecasted power generation curve from renewable sources, different tariffs' rates, electric circuit constraints, user restrictions and correspondent comfort levels. Given these considerations, this work defines and evaluates a distributed micro grid resource management architecture and protocol which is able to optimize load scheduling while considering all the mentioned restrictions and parameters. The proposed architecture was implemented on a multi-agent simulator and the performed tests show that significant reductions in electricity cost can be achieved using this methodology. © 2014 IEEE.
- A visual programming language for soccerPublication . Belguinha, António; Rodrigues, Pedro; Cardoso, Pedro J. S.; Rodrigues, J. M. F.; Paciência, DomingosThe use of Information Technologies (IT) in high competition sports is an instrument often used. However, the majority of the performers, including technical teams, do not have skills to program those IT tools to their needs. In this paper we present the low level implementation of a visual programming language (VPL) that allows the user without programming expertise to produce relatively complex programs by drawing them on a web application. The VPL tool application is illustrated by applying it to detect programmed situations from a soccer game, using previously obtained tracking data. The tool can be applied to other collective ball sports.
- Ant colony algorithms for multiple objective combinatorial optimization: applications to the minimum spanning trees problemsPublication . Cardoso, Pedro J. S.The study of meta-heuristic solutions based on the Ant Colony Optimization (ACO) paradigm for the Multiple Objective Minimum Spanning Trees and related combinatorial problems is the main concern of this investigation. In the commonly accepted complexity scale for problems, the Multiple Objective Minimum Spanning Trees is rated as an $\NP$-complete problem. Furthermore, as in the generality of the multiple objective optimization problem, the solution of the Minimum Spanning Trees case is a set of trade-off solutions in the sense that to improve one of the objectives it is necessary to worse at least one of the others, which is a major concern in a practical point of view. In the first part of the investigation, a theoretical analysis of the problem is made to complement the known results. This analysis corroborates the fact that in practice the use of exact methods to solve the Multiple Objective Minimum Spanning Trees problems is only applied in specific circumstances. This implies that to solve the problem an approximation method must be considered as an alternative. In particular, two methods based on the ACO paradigm are proposed: the Multiple Objective Network optimization based on an ACO (MONACO) and the $\epsilon$-Depth ANT Explorer (e-DANTE). The MONACO method uses a set of pheromone trails and specific heuristics to approximate the Pareto set. The e-DANTE method is an improvement of the MONACO method that uses a depth search procedure, based on the best performing solutions, to deeply exploit the search space. The proposed methods are tested with selected multiple objective problems, improving the results previously obtained by other authors. To test the MONACO and e-DANTE algorithms over the Multiple Objective Minimum Spanning Trees problem is proposed a library/repository of multiple objective network problems established over a systematized set of networks generators. The results obtained with MONACO and e-DANTE are then compared with the results obtained with a Brute Force and the Weighted Sum method.
- Ant colony optimization routing mechanisms with bandwidth sensingPublication . Mapisse, J. M.; Cardoso, Pedro J. S.; Monteiro, J. M.The study and understanding of the social behavior of insects has contributed to the definition of some algorithms that are capable of solving several types of optimization problems. In 1997 Di Caro and Dorigo developed the first routing algorithm for wired networks, called AntNet, using an approach which was inspired in the behavior of ant colonies. At each node, AntNet, similar to others Ant Colony Optimization (ACO) based algorithms, forward ants based in the amount of pheromones present in the links and in response to the node's queue lengths. In this paper, an adaptation of the e-DANTE algorithm for discrete problems, as an IP based routing mechanism, was implemented. We also propose the inclusion of a new parameter for the computation of paths for both the AntNet and the newly proposed algorithm: the available bandwith. Those methods were tested in ns-2 using two dense network architectures and their efficiency is compared with the original AntNet and a Link-State routing algorithm, when considering the transmission of competing traffic flows between distinct nodes. © 2011 IEEE.
- Augmented reality and holograms for the visualization of mechanical engineering partsPublication . Figueiredo, Mauro; Cardoso, Pedro J. S.; Gonçalves, C. D. F.; Rodrigues, J. M. F.There is an increasing number of students using tablets in schools. Mobile devices gained popularity as an educational tool and there are many schools that use them frequently in educational activities to improve learning. We found that first year students of mechanical engineering in general have difficulties in understanding 3D shapes from 2D views. There are many Augmented Reality (AR) applications available that can be used to create educational contents for these mobile devices. On the other hand, there is an increasing interest in making holograms. In this paper we studied the most popular AR systems and show examples of using an AR system for the visualization of 3D models. We also present the creation of a low cost prototype, the EducHolo, that enables the visualization of holograms supported by tablets. With this prototype students can visualize the hologram of mechanical parts, providing a better perception of the model 3D shape and improving the ability of making the 2D orthographic views and perspectives that they study in the first year of mechanical engineer.
- DANTE - The combination between an ant colony optimization algorithm and a depth search methodPublication . Cardoso, Pedro J. S.; Jesus, Mário; Marquez, AlbertoThe ε-DANTE method is an hybrid meta-heuristic. In combines the evolutionary Ant Colony Optimization (ACO) algorithms with a limited Depth Search. This Depth Search is based in the pheromone trails used by the ACO, which allows it to be oriented to the more promising areas of the search space. Some results are presented for the multiple objective k-Degree Spanning Trees problem, proving the effectiveness of the method when compared with other already tested evolutionary methods. © 2008 IEEE.
- Detection, classification and localisation of football players and ball from handycam videosPublication . Vilas, Tiago; Rodrigues, J. M. F.; Cardoso, Pedro J. S.The current performance requirements in football make imperative the use of new technologies for game observation and analysis, providing detailed information about the team's actions. This paper presents in resume an algorithm to collect information from Handycam videos, namely, the football pitch, player and ball detection, player classification within the team, the tracking and localisation of players and ball, being the main contribution the determination of the exact localisation of players and ball in the pitch.
- epsilon-DANTE: an ant colony oriented depth search procedurePublication . Cardoso, Pedro J. S.; Jesus, Mário; Marquez, AlbertoThe epsilon-Depth ANT Explorer (epsilon-DANTE) algorithm applied to a multiple objective optimization problem is presented in this paper. This method is a hybridization of the ant colony optimization algorithm with a depth search procedure, putting together an oriented/limited depth search. A particular design of the pheromone set of rules is suggested for these kinds of optimization problems, which are an adaptation of the single objective case. Six versions with incremental features are presented as an evolutive path, beginning in a single colony approach, where no depth search is applied, to the final epsilon-DANTE. Versions are compared among themselves in a set of instances of the multiple objective Traveling Salesman Problem. Finally, our best version of epsilon-DANTE is compared with several established heuristics in the field showing some promising results.
- Evaluation of the human factor in the scheduling of smart appliances in smart gridsPublication . Monteiro, J. M.; Cardoso, Pedro J. S.; Serra, R.; Fernandes, L.Recently there has been an increase of interest in implementing a new set of home appliances, known as Smart Appliances that integrate Information Technologies, the Internet of Things and the ability of communicating with other devices. While Smart Appliances are characterized as an important milestone on the path to the Smart Grid, by being able to automatically schedule their loads according to a tariff or reflecting the power that is generated using renewable sources, there is not a clear understanding on the impact that the behavior of such devices will have in the comfort levels of users, when they shift their working periods to earlier, or later than, a preset time. Given these considerations, in this work we analyse the results of an assessment survey carried out to a group of Home Appliance users regarding their habits when dealing with these machines and the subjective impact in quality caused by either finishing its programs before or after the time limit set by the user. The results of this work are expected to be used as input for the evaluation of load scheduling algorithms running in energy management systems. © 2014 Springer International Publishing.